Purpose
This developmental study explored the conceptual feasibility and applicability of a metaverse-based clinical assessment platform as a complementary tool to conventional objective structured clinical examinations in undergraduate medical education.
Methods
A targeted literature review and expert consensus process were conducted to identify domains of clinical competence in which metaverse technologies could provide added value. Based on these findings, prototype virtual patient simulations were developed within a metaverse environment. Large language models (LLMs) were integrated to support dynamic, interactive history-taking simulations, and pilot modules for physical examination were also created.
Results
Integration of LLMs into virtual patient scenarios enabled realistic, context-sensitive medical interviews, facilitating interactive dialogue between examinees and simulated patients. In contrast, physical examination modules faced technical limitations, particularly in replicating procedures requiring tactile or haptic feedback, such as palpation and percussion. Nevertheless, the metaverse environment enabled delivery of consistent and reproducible scenarios, supporting objective assessment of communication and diagnostic reasoning skills.
Conclusion
Metaverse-based simulations augmented by LLMs offer a promising approach to scalable and standardized clinical assessment, particularly within cognitive and interpersonal competency domains. Although current technological constraints limit the fidelity of physical examination simulations, rapid advancements in immersive and haptic technologies may help overcome these barriers in the near future. Further research is needed to evaluate the educational efficacy, validity, and feasibility of deploying such platforms in summative, high-stakes assessment contexts.

Purpose
To develop and evaluate a large language model (LLM)-based learning tool, featuring virtual patients (VPs) and virtual assessors (VAs), and to assess its impact on medical students’ perceptions of history-taking education compared to conventional learning methods.
Methods
A tool using the GPT-4 API was developed to provide seven clinical VP scenarios and a VA that delivered both immediate, reflective dialogue and comprehensive written feedback. First- and second-year medical students participated in a 6-day study. Pre- and post-participation surveys using a 5-point Likert scale assessed perceptions of the LLM tool versus conventional methods across usability, self-efficacy, and feedback quality domains.
Results
Twenty-one students completed the study. The LLM-based tool demonstrated statistically significant improvements over conventional methods in all assessed domains. Students reported greater comfort during practice (mean 4.57 vs. 2.95, p=0.0002). Significant gains were seen in six of eight self-efficacy measures, including confidence in handling unfamiliar cases (4.00 vs. 2.90, p=0.0002). All nine feedback quality dimensions improved significantly, with feedback perceived as more specific (4.43 vs. 3.24, p=0.0005) and personalized (4.19 vs. 3.19, p=0.0001).
Conclusion
An LLM-based learning tool featuring VPs and VAs can significantly enhance medical students’ perceived learning experience in history-taking education. It offers a scalable, accessible, and cost-effective complementary training method. Future research should validate these subjective improvements with objective performance metrics.

Purpose
Maintaining the quality of Single Best Answer (SBA) questions remains a challenge in medical education, especially as artificial intelligence (AI)-generated items become more common. While considerable attention has been paid to AI question generation, the vetting process is under-explored and difficult to scale.
Methods
This study investigates the feasibility and reliability of using a large language model to support the vetting of SBA questions. An AI-based reviewer, QA-bot, was developed using custom GPT and embedded with 25 criteria aligned with Bloom’s taxonomy (Levels 1–3). QA-bot and two experienced educators independently evaluated 32 AI-generated SBA questions using the shared evaluation rubric.
Results
The rubric showed high internal consistency (Cronbach’s alpha=0.878), and strong inter-rater reliability between human reviewers (intraclass correlation coefficient [ICC]=0.893). QA-bot demonstrated good alignment with human raters (ICC=0.861 and 0.840). While the AI performed well on objective, rule-based criteria, it was less consistent in detecting irrelevant complexity and accurately judging difficulty.
Conclusion
These findings suggest that AI can function as an efficient first-pass reviewer, improving consistency and reducing workload, with human oversight remaining essential for educational and clinical relevance.